1 files changed, 306 insertions, 151 deletions

diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 7754d51e1c27..8712b891defb 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -44,7 +44,7 @@ xfs_fsmap_from_internal(
 }
 
 /* Convert an fsmap to an xfs_fsmap. */
-void
+static void
 xfs_fsmap_to_internal(
 	struct xfs_fsmap	*dest,
 	struct fsmap		*src)
@@ -162,6 +162,8 @@ struct xfs_getfsmap_info {
 	xfs_daddr_t		next_daddr;	/* next daddr we expect */
 	/* daddr of low fsmap key when we're using the rtbitmap */
 	xfs_daddr_t		low_daddr;
+	/* daddr of high fsmap key, or the last daddr on the device */
+	xfs_daddr_t		end_daddr;
 	u64			missing_owner;	/* owner of holes */
 	u32			dev;		/* device id */
 	/*
@@ -182,6 +184,7 @@ struct xfs_getfsmap_dev {
 	int			(*fn)(struct xfs_trans *tp,
 				      const struct xfs_fsmap *keys,
 				      struct xfs_getfsmap_info *info);
+	sector_t		nr_sectors;
 };
 
 /* Compare two getfsmap device handlers. */
@@ -294,6 +297,18 @@ xfs_getfsmap_helper(
 		return 0;
 	}
 
+	/*
+	 * For an info->last query, we're looking for a gap between the last
+	 * mapping emitted and the high key specified by userspace.  If the
+	 * user's query spans less than 1 fsblock, then info->high and
+	 * info->low will have the same rm_startblock, which causes rec_daddr
+	 * and next_daddr to be the same.  Therefore, use the end_daddr that
+	 * we calculated from userspace's high key to synthesize the record.
+	 * Note that if the btree query found a mapping, there won't be a gap.
+	 */
+	if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL)
+		rec_daddr = info->end_daddr + 1;
+
 	/* Are we just counting mappings? */
 	if (info->head->fmh_count == 0) {
 		if (info->head->fmh_entries == UINT_MAX)
@@ -427,144 +442,6 @@ xfs_getfsmap_set_irec_flags(
 		irec->rm_flags |= XFS_RMAP_UNWRITTEN;
 }
 
-/* Execute a getfsmap query against the log device. */
-STATIC int
-xfs_getfsmap_logdev(
-	struct xfs_trans		*tp,
-	const struct xfs_fsmap		*keys,
-	struct xfs_getfsmap_info	*info)
-{
-	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_rmap_irec		rmap;
-	xfs_daddr_t			rec_daddr, len_daddr;
-	xfs_fsblock_t			start_fsb, end_fsb;
-	uint64_t			eofs;
-
-	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
-	if (keys[0].fmr_physical >= eofs)
-		return 0;
-	start_fsb = XFS_BB_TO_FSBT(mp,
-				keys[0].fmr_physical + keys[0].fmr_length);
-	end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
-
-	/* Adjust the low key if we are continuing from where we left off. */
-	if (keys[0].fmr_length > 0)
-		info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb);
-
-	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb);
-	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb);
-
-	if (start_fsb > 0)
-		return 0;
-
-	/* Fabricate an rmap entry for the external log device. */
-	rmap.rm_startblock = 0;
-	rmap.rm_blockcount = mp->m_sb.sb_logblocks;
-	rmap.rm_owner = XFS_RMAP_OWN_LOG;
-	rmap.rm_offset = 0;
-	rmap.rm_flags = 0;
-
-	rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock);
-	len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount);
-	return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr);
-}
-
-#ifdef CONFIG_XFS_RT
-/* Transform a rtbitmap "record" into a fsmap */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap_helper(
-	struct xfs_mount		*mp,
-	struct xfs_trans		*tp,
-	const struct xfs_rtalloc_rec	*rec,
-	void				*priv)
-{
-	struct xfs_getfsmap_info	*info = priv;
-	struct xfs_rmap_irec		irec;
-	xfs_rtblock_t			rtbno;
-	xfs_daddr_t			rec_daddr, len_daddr;
-
-	rtbno = rec->ar_startext * mp->m_sb.sb_rextsize;
-	rec_daddr = XFS_FSB_TO_BB(mp, rtbno);
-	irec.rm_startblock = rtbno;
-
-	rtbno = rec->ar_extcount * mp->m_sb.sb_rextsize;
-	len_daddr = XFS_FSB_TO_BB(mp, rtbno);
-	irec.rm_blockcount = rtbno;
-
-	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
-	irec.rm_offset = 0;
-	irec.rm_flags = 0;
-
-	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr);
-}
-
-/* Execute a getfsmap query against the realtime device rtbitmap. */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap(
-	struct xfs_trans		*tp,
-	const struct xfs_fsmap		*keys,
-	struct xfs_getfsmap_info	*info)
-{
-
-	struct xfs_rtalloc_rec		alow = { 0 };
-	struct xfs_rtalloc_rec		ahigh = { 0 };
-	struct xfs_mount		*mp = tp->t_mountp;
-	xfs_rtblock_t			start_rtb;
-	xfs_rtblock_t			end_rtb;
-	uint64_t			eofs;
-	int				error;
-
-	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rextents * mp->m_sb.sb_rextsize);
-	if (keys[0].fmr_physical >= eofs)
-		return 0;
-	start_rtb = XFS_BB_TO_FSBT(mp,
-				keys[0].fmr_physical + keys[0].fmr_length);
-	end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
-
-	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
-
-	/* Adjust the low key if we are continuing from where we left off. */
-	if (keys[0].fmr_length > 0) {
-		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
-		if (info->low_daddr >= eofs)
-			return 0;
-	}
-
-	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb);
-	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb);
-
-	xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-
-	/*
-	 * Set up query parameters to return free rtextents covering the range
-	 * we want.
-	 */
-	alow.ar_startext = start_rtb;
-	ahigh.ar_startext = end_rtb;
-	do_div(alow.ar_startext, mp->m_sb.sb_rextsize);
-	if (do_div(ahigh.ar_startext, mp->m_sb.sb_rextsize))
-		ahigh.ar_startext++;
-	error = xfs_rtalloc_query_range(mp, tp, &alow, &ahigh,
-			xfs_getfsmap_rtdev_rtbitmap_helper, info);
-	if (error)
-		goto err;
-
-	/*
-	 * Report any gaps at the end of the rtbitmap by simulating a null
-	 * rmap starting at the block after the end of the query range.
-	 */
-	info->last = true;
-	ahigh.ar_startext = min(mp->m_sb.sb_rextents, ahigh.ar_startext);
-
-	error = xfs_getfsmap_rtdev_rtbitmap_helper(mp, tp, &ahigh, info);
-	if (error)
-		goto err;
-err:
-	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
-	return error;
-}
-#endif /* CONFIG_XFS_RT */
-
 static inline bool
 rmap_not_shareable(struct xfs_mount *mp, const struct xfs_rmap_irec *r)
 {
@@ -766,8 +643,8 @@ xfs_getfsmap_datadev_bnobt_query(
 		return xfs_getfsmap_datadev_bnobt_helper(*curpp, &key[1], info);
 
 	/* Allocate cursor for this AG and query_range it. */
-	*curpp = xfs_allocbt_init_cursor(tp->t_mountp, tp, info->agf_bp,
-			info->pag, XFS_BTNUM_BNO);
+	*curpp = xfs_bnobt_init_cursor(tp->t_mountp, tp, info->agf_bp,
+			info->pag);
 	key->ar_startblock = info->low.rm_startblock;
 	key[1].ar_startblock = info->high.rm_startblock;
 	return xfs_alloc_query_range(*curpp, key, &key[1],
@@ -789,6 +666,140 @@ xfs_getfsmap_datadev_bnobt(
 			xfs_getfsmap_datadev_bnobt_query, &akeys[0]);
 }
 
+/* Execute a getfsmap query against the log device. */
+STATIC int
+xfs_getfsmap_logdev(
+	struct xfs_trans		*tp,
+	const struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_rmap_irec		rmap;
+	xfs_daddr_t			rec_daddr, len_daddr;
+	xfs_fsblock_t			start_fsb, end_fsb;
+	uint64_t			eofs;
+
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	start_fsb = XFS_BB_TO_FSBT(mp,
+				keys[0].fmr_physical + keys[0].fmr_length);
+	end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
+
+	/* Adjust the low key if we are continuing from where we left off. */
+	if (keys[0].fmr_length > 0)
+		info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb);
+
+	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb);
+	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb);
+
+	if (start_fsb > 0)
+		return 0;
+
+	/* Fabricate an rmap entry for the external log device. */
+	rmap.rm_startblock = 0;
+	rmap.rm_blockcount = mp->m_sb.sb_logblocks;
+	rmap.rm_owner = XFS_RMAP_OWN_LOG;
+	rmap.rm_offset = 0;
+	rmap.rm_flags = 0;
+
+	rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock);
+	len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount);
+	return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr);
+}
+
+#ifdef CONFIG_XFS_RT
+/* Transform a rtbitmap "record" into a fsmap */
+STATIC int
+xfs_getfsmap_rtdev_rtbitmap_helper(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	const struct xfs_rtalloc_rec	*rec,
+	void				*priv)
+{
+	struct xfs_getfsmap_info	*info = priv;
+	struct xfs_rmap_irec		irec;
+	xfs_rtblock_t			rtbno;
+	xfs_daddr_t			rec_daddr, len_daddr;
+
+	rtbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
+	rec_daddr = XFS_FSB_TO_BB(mp, rtbno);
+	irec.rm_startblock = rtbno;
+
+	rtbno = xfs_rtx_to_rtb(mp, rec->ar_extcount);
+	len_daddr = XFS_FSB_TO_BB(mp, rtbno);
+	irec.rm_blockcount = rtbno;
+
+	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
+	irec.rm_offset = 0;
+	irec.rm_flags = 0;
+
+	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr);
+}
+
+/* Execute a getfsmap query against the realtime device rtbitmap. */
+STATIC int
+xfs_getfsmap_rtdev_rtbitmap(
+	struct xfs_trans		*tp,
+	const struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info)
+{
+
+	struct xfs_rtalloc_rec		ahigh = { 0 };
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_rtblock_t			start_rtb;
+	xfs_rtblock_t			end_rtb;
+	xfs_rtxnum_t			high;
+	uint64_t			eofs;
+	int				error;
+
+	eofs = XFS_FSB_TO_BB(mp, xfs_rtx_to_rtb(mp, mp->m_sb.sb_rextents));
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	start_rtb = XFS_BB_TO_FSBT(mp,
+				keys[0].fmr_physical + keys[0].fmr_length);
+	end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical));
+
+	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
+
+	/* Adjust the low key if we are continuing from where we left off. */
+	if (keys[0].fmr_length > 0) {
+		info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb);
+		if (info->low_daddr >= eofs)
+			return 0;
+	}
+
+	trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb);
+	trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb);
+
+	xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
+
+	/*
+	 * Set up query parameters to return free rtextents covering the range
+	 * we want.
+	 */
+	high = xfs_rtb_to_rtxup(mp, end_rtb);
+	error = xfs_rtalloc_query_range(mp, tp, xfs_rtb_to_rtx(mp, start_rtb),
+			high, xfs_getfsmap_rtdev_rtbitmap_helper, info);
+	if (error)
+		goto err;
+
+	/*
+	 * Report any gaps at the end of the rtbitmap by simulating a null
+	 * rmap starting at the block after the end of the query range.
+	 */
+	info->last = true;
+	ahigh.ar_startext = min(mp->m_sb.sb_rextents, high);
+
+	error = xfs_getfsmap_rtdev_rtbitmap_helper(mp, tp, &ahigh, info);
+	if (error)
+		goto err;
+err:
+	xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+	return error;
+}
+#endif /* CONFIG_XFS_RT */
+
 /* Do we recognize the device? */
 STATIC bool
 xfs_getfsmap_is_valid_device(
@@ -879,7 +890,7 @@ xfs_getfsmap_check_keys(
  * xfs_getfsmap_info.low/high	-- per-AG low/high keys computed from
  *				   dkeys; used to query the metadata.
  */
-int
+STATIC int
 xfs_getfsmap(
 	struct xfs_mount		*mp,
 	struct xfs_fsmap_head		*head,
@@ -888,7 +899,10 @@ xfs_getfsmap(
 	struct xfs_trans		*tp = NULL;
 	struct xfs_fsmap		dkeys[2];	/* per-dev keys */
 	struct xfs_getfsmap_dev		handlers[XFS_GETFSMAP_DEVS];
-	struct xfs_getfsmap_info	info = { NULL };
+	struct xfs_getfsmap_info	info = {
+		.fsmap_recs		= fsmap_recs,
+		.head			= head,
+	};
 	bool				use_rmap;
 	int				i;
 	int				error = 0;
@@ -907,17 +921,21 @@ xfs_getfsmap(
 
 	/* Set up our device handlers. */
 	memset(handlers, 0, sizeof(handlers));
+	handlers[0].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
 	handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev);
 	if (use_rmap)
 		handlers[0].fn = xfs_getfsmap_datadev_rmapbt;
 	else
 		handlers[0].fn = xfs_getfsmap_datadev_bnobt;
 	if (mp->m_logdev_targp != mp->m_ddev_targp) {
+		handlers[1].nr_sectors = XFS_FSB_TO_BB(mp,
+						       mp->m_sb.sb_logblocks);
 		handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev);
 		handlers[1].fn = xfs_getfsmap_logdev;
 	}
 #ifdef CONFIG_XFS_RT
 	if (mp->m_rtdev_targp) {
+		handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
 		handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
 		handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
 	}
@@ -949,8 +967,6 @@ xfs_getfsmap(
 
 	info.next_daddr = head->fmh_keys[0].fmr_physical +
 			  head->fmh_keys[0].fmr_length;
-	info.fsmap_recs = fsmap_recs;
-	info.head = head;
 
 	/* For each device we support... */
 	for (i = 0; i < XFS_GETFSMAP_DEVS; i++) {
@@ -963,14 +979,23 @@ xfs_getfsmap(
 			break;
 
 		/*
-		 * If this device number matches the high key, we have
-		 * to pass the high key to the handler to limit the
-		 * query results.  If the device number exceeds the
-		 * low key, zero out the low key so that we get
-		 * everything from the beginning.
+		 * If this device number matches the high key, we have to pass
+		 * the high key to the handler to limit the query results, and
+		 * set the end_daddr so that we can synthesize records at the
+		 * end of the query range or device.
 		 */
-		if (handlers[i].dev == head->fmh_keys[1].fmr_device)
+		if (handlers[i].dev == head->fmh_keys[1].fmr_device) {
 			dkeys[1] = head->fmh_keys[1];
+			info.end_daddr = min(handlers[i].nr_sectors - 1,
+					     dkeys[1].fmr_physical);
+		} else {
+			info.end_daddr = handlers[i].nr_sectors - 1;
+		}
+
+		/*
+		 * If the device number exceeds the low key, zero out the low
+		 * key so that we get everything from the beginning.
+		 */
 		if (handlers[i].dev > head->fmh_keys[0].fmr_device)
 			memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));
 
@@ -1001,3 +1026,133 @@ xfs_getfsmap(
 	head->fmh_oflags = FMH_OF_DEV_T;
 	return error;
 }
+
+int
+xfs_ioc_getfsmap(
+	struct xfs_inode	*ip,
+	struct fsmap_head	__user *arg)
+{
+	struct xfs_fsmap_head	xhead = {0};
+	struct fsmap_head	head;
+	struct fsmap		*recs;
+	unsigned int		count;
+	__u32			last_flags = 0;
+	bool			done = false;
+	int			error;
+
+	if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
+		return -EFAULT;
+	if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) ||
+	    memchr_inv(head.fmh_keys[0].fmr_reserved, 0,
+		       sizeof(head.fmh_keys[0].fmr_reserved)) ||
+	    memchr_inv(head.fmh_keys[1].fmr_reserved, 0,
+		       sizeof(head.fmh_keys[1].fmr_reserved)))
+		return -EINVAL;
+
+	/*
+	 * Use an internal memory buffer so that we don't have to copy fsmap
+	 * data to userspace while holding locks.  Start by trying to allocate
+	 * up to 128k for the buffer, but fall back to a single page if needed.
+	 */
+	count = min_t(unsigned int, head.fmh_count,
+			131072 / sizeof(struct fsmap));
+	recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL);
+	if (!recs) {
+		count = min_t(unsigned int, head.fmh_count,
+				PAGE_SIZE / sizeof(struct fsmap));
+		recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL);
+		if (!recs)
+			return -ENOMEM;
+	}
+
+	xhead.fmh_iflags = head.fmh_iflags;
+	xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]);
+	xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]);
+
+	trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
+	trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]);
+
+	head.fmh_entries = 0;
+	do {
+		struct fsmap __user	*user_recs;
+		struct fsmap		*last_rec;
+
+		user_recs = &arg->fmh_recs[head.fmh_entries];
+		xhead.fmh_entries = 0;
+		xhead.fmh_count = min_t(unsigned int, count,
+					head.fmh_count - head.fmh_entries);
+
+		/* Run query, record how many entries we got. */
+		error = xfs_getfsmap(ip->i_mount, &xhead, recs);
+		switch (error) {
+		case 0:
+			/*
+			 * There are no more records in the result set.  Copy
+			 * whatever we got to userspace and break out.
+			 */
+			done = true;
+			break;
+		case -ECANCELED:
+			/*
+			 * The internal memory buffer is full.  Copy whatever
+			 * records we got to userspace and go again if we have
+			 * not yet filled the userspace buffer.
+			 */
+			error = 0;
+			break;
+		default:
+			goto out_free;
+		}
+		head.fmh_entries += xhead.fmh_entries;
+		head.fmh_oflags = xhead.fmh_oflags;
+
+		/*
+		 * If the caller wanted a record count or there aren't any
+		 * new records to return, we're done.
+		 */
+		if (head.fmh_count == 0 || xhead.fmh_entries == 0)
+			break;
+
+		/* Copy all the records we got out to userspace. */
+		if (copy_to_user(user_recs, recs,
+				 xhead.fmh_entries * sizeof(struct fsmap))) {
+			error = -EFAULT;
+			goto out_free;
+		}
+
+		/* Remember the last record flags we copied to userspace. */
+		last_rec = &recs[xhead.fmh_entries - 1];
+		last_flags = last_rec->fmr_flags;
+
+		/* Set up the low key for the next iteration. */
+		xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec);
+		trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
+	} while (!done && head.fmh_entries < head.fmh_count);
+
+	/*
+	 * If there are no more records in the query result set and we're not
+	 * in counting mode, mark the last record returned with the LAST flag.
+	 */
+	if (done && head.fmh_count > 0 && head.fmh_entries > 0) {
+		struct fsmap __user	*user_rec;
+
+		last_flags |= FMR_OF_LAST;
+		user_rec = &arg->fmh_recs[head.fmh_entries - 1];
+
+		if (copy_to_user(&user_rec->fmr_flags, &last_flags,
+					sizeof(last_flags))) {
+			error = -EFAULT;
+			goto out_free;
+		}
+	}
+
+	/* copy back header */
+	if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) {
+		error = -EFAULT;
+		goto out_free;
+	}
+
+out_free:
+	kvfree(recs);
+	return error;
+}